Results 1 to 10 of about 202,230 (228)

LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of End-to-End ASR Models [PDF]

open access: greenAutomatic Speech Recognition & Understanding, 2023
Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format.
Aleksandr Meister   +5 more
semanticscholar   +3 more sources

Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition [PDF]

open access: diamondInternational Journal on Natural Language Computing, 2022
While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting from irregular
Piyush Behre   +3 more
semanticscholar   +2 more sources

Digital Support for Teaching Punctuation in Academic Writing in English

open access: yesJournal of Language and Education, 2022
Background. Academic writing skills are crucial to the enterprise of higher education, because much of the academic communication is in writing. As a rule, foreign language learners face different problems with vocabulary misuse, grammatical errors ...
Marina Ivanova   +2 more
doaj   +2 more sources

Is Arabic punctuation rule-governed?

open access: yesCogent Arts & Humanities
This paper investigates the extent to which Arabic punctuation is rule-governed, with the aim of improving text comprehension, disambiguation, and machine translation.
Sane Yagi   +5 more
doaj   +2 more sources

Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Merging [PDF]

open access: greenOriental COCOSDA International Conference on Speech Database and Assessments, 2019
In recent years, studies on automatic speech recognition (ASR) have shown outstanding results that reach human parity on short speech segments.
Thai-Binh Nguyen   +6 more
semanticscholar   +3 more sources

Multifractal Hopscotch in Hopscotch by Julio Cortázar [PDF]

open access: yesEntropy
Punctuation is the main factor introducing correlations in natural language written texts and it crucially impacts their overall effectiveness, expressiveness, and readability.
Jakub Dec   +4 more
doaj   +2 more sources

Analyzing atudents’ awareness of using appropriate punctuation marks in dialogue text (a descriptive study with eighth grade students of MTs Darul Ulum Semarang in the academic year of 2009/2010) [PDF]

open access: green, 2010
The background of this study is based on phenomenon that the use of punctuation marks were often less considered by the eighth grade students of MTs Darul Ulum Semarang in the academic year of 2009/2010.
Anwar, Saekul
core   +2 more sources

Libriheavy: A 50,000 Hours ASR Corpus with Punctuation Casing and Context [PDF]

open access: yesIEEE International Conference on Acoustics, Speech, and Signal Processing, 2023
In this paper, we introduce Libriheavy, a large-scale ASR corpus consisting of 50,000 hours of read English speech derived from LibriVox. To the best of our knowledge, Libriheavy is the largest freely-available corpus of speech with supervisions ...
Wei Kang   +7 more
semanticscholar   +1 more source

Where’s the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation [PDF]

open access: yesAnnual Meeting of the Association for Computational Linguistics, 2023
Many NLP pipelines split text into sentences as one of the crucial preprocessing steps. Prior sentence segmentation tools either rely on punctuation or require a considerable amount of sentence-segmented training data: both central assumptions might fail
Benjamin Minixhofer   +2 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy